Compliant control vs pure position control for insertion tasks - preferences?

End effectors, dexterous hands, tendon drives, tactile fingertips, grasp planning, and teleoperation.
camila.jackson0
Posts: 225
Joined: Wed Oct 09, 2024 1:27 am

Re: Compliant control vs pure position control for insertion tasks - preferences?

Post by camila.jackson0 »

That's the official framing, at least - reality tends to lag a bit. In-hand reorientation (repositioning a grasped object without setting it down) is one of the more advanced manipulation skills, requiring either a highly dexterous hand with enough DoF or clever use of gravity and controlled slipping - it's an active research area rather than a solved problem. Imitation learning from human demonstration video (without robot teleoperation data) is an appealing way to scale up training data cheaply, but it runs into the embodiment gap - human hand kinematics and force profiles don't map directly onto a robot hand's very different mechanism.
Building > buying.
sven.smith4
Posts: 60
Joined: Sat Feb 28, 2026 3:48 pm

Re: Compliant control vs pure position control for insertion tasks - preferences?

Post by sven.smith4 »

Speaking from personal experience here, Figure's fourth-generation Dexterous Hand (on Figure 02/03) reportedly offers 16 degrees of freedom per hand with sensors integrated into each finger, aimed at fine force control tasks like handling small electronic components without crushing them. In-hand reorientation (repositioning a grasped object without setting it down) is one of the more advanced manipulation skills, requiring either a highly dexterous hand with enough DoF or clever use of gravity and controlled slipping - it's an active research area rather than a solved problem.
Opinions my own, not my employer's.
scott21
Posts: 256
Joined: Fri Oct 11, 2024 9:57 am

Re: Compliant control vs pure position control for insertion tasks - preferences?

Post by scott21 »

@sven.smith4 Same conclusion I've come to. Also worth noting: Bimanual manipulation - two arms coordinating on one task - is harder than it looks mostly because of the added degrees of freedom and the timing/force coordination required; a lot of 'two-handed' demos are actually closer to two independent single-hand tasks done in sequence.
she/her
diego.moore6
Posts: 155
Joined: Thu May 08, 2025 8:48 am

Re: Compliant control vs pure position control for insertion tasks - preferences?

Post by diego.moore6 »

@scott21 Small correction on one detail: Grasp planning for deformable or non-rigid objects (bags, cables, cloth) remains one of the genuinely unsolved problems in manipulation - rigid-body grasp models simply don't capture how the object will behave once contact starts. In-hand reorientation (repositioning a grasped object without setting it down) is one of the more advanced manipulation skills, requiring either a highly dexterous hand with enough DoF or clever use of gravity and controlled slipping - it's an active research area rather than a solved problem.
Building > buying.
Post Reply